{ "best_metric": NaN, "best_model_checkpoint": "miner_id_24/checkpoint-25", "epoch": 1.5194312796208531, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.03033175355450237, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.03033175355450237, "eval_loss": NaN, "eval_runtime": 4.1249, "eval_samples_per_second": 12.121, "eval_steps_per_second": 3.152, "step": 1 }, { "epoch": 0.06066350710900474, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 2 }, { "epoch": 0.0909952606635071, "grad_norm": NaN, "learning_rate": 9.990365154573717e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.12132701421800948, "grad_norm": NaN, "learning_rate": 9.961501876182148e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.15165876777251186, "grad_norm": NaN, "learning_rate": 9.913533761814537e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.1819905213270142, "grad_norm": NaN, "learning_rate": 9.846666218300807e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.2123222748815166, "grad_norm": NaN, "learning_rate": 9.761185582727977e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.24265402843601896, "grad_norm": NaN, "learning_rate": 9.657457896300791e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.2729857819905213, "grad_norm": NaN, "learning_rate": 9.535927336897098e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.3033175355450237, "grad_norm": NaN, "learning_rate": 9.397114317029975e-05, "loss": 0.0, "step": 10 }, { "epoch": 0.33364928909952607, "grad_norm": NaN, "learning_rate": 9.241613255361455e-05, "loss": 0.0, "step": 11 }, { "epoch": 0.3639810426540284, "grad_norm": NaN, "learning_rate": 9.070090031310558e-05, "loss": 0.0, "step": 12 }, { "epoch": 0.3943127962085308, "grad_norm": NaN, "learning_rate": 8.883279133655399e-05, "loss": 0.0, "step": 13 }, { "epoch": 0.4246445497630332, "grad_norm": NaN, "learning_rate": 8.681980515339464e-05, "loss": 0.0, "step": 14 }, { "epoch": 0.4549763033175355, "grad_norm": NaN, "learning_rate": 8.467056167950311e-05, "loss": 0.0, "step": 15 }, { "epoch": 0.48530805687203793, "grad_norm": NaN, "learning_rate": 8.239426430539243e-05, "loss": 0.0, "step": 16 }, { "epoch": 0.5156398104265403, "grad_norm": NaN, "learning_rate": 8.000066048588211e-05, "loss": 0.0, "step": 17 }, { "epoch": 0.5459715639810426, "grad_norm": NaN, "learning_rate": 7.75e-05, "loss": 0.0, "step": 18 }, { "epoch": 0.576303317535545, "grad_norm": NaN, "learning_rate": 7.490299105985507e-05, "loss": 0.0, "step": 19 }, { "epoch": 0.6066350710900474, "grad_norm": NaN, "learning_rate": 7.222075445642904e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.6369668246445498, "grad_norm": NaN, "learning_rate": 6.946477593864228e-05, "loss": 0.0, "step": 21 }, { "epoch": 0.6672985781990521, "grad_norm": NaN, "learning_rate": 6.664685702961344e-05, "loss": 0.0, "step": 22 }, { "epoch": 0.6976303317535545, "grad_norm": NaN, "learning_rate": 6.377906449072578e-05, "loss": 0.0, "step": 23 }, { "epoch": 0.7279620853080568, "grad_norm": NaN, "learning_rate": 6.087367864990233e-05, "loss": 0.0, "step": 24 }, { "epoch": 0.7582938388625592, "grad_norm": NaN, "learning_rate": 5.794314081535644e-05, "loss": 0.0, "step": 25 }, { "epoch": 0.7582938388625592, "eval_loss": NaN, "eval_runtime": 4.1593, "eval_samples_per_second": 12.021, "eval_steps_per_second": 3.126, "step": 25 }, { "epoch": 0.7886255924170616, "grad_norm": NaN, "learning_rate": 5.500000000000001e-05, "loss": 0.0, "step": 26 }, { "epoch": 0.818957345971564, "grad_norm": NaN, "learning_rate": 5.205685918464356e-05, "loss": 0.0, "step": 27 }, { "epoch": 0.8492890995260663, "grad_norm": NaN, "learning_rate": 4.912632135009769e-05, "loss": 0.0, "step": 28 }, { "epoch": 0.8796208530805687, "grad_norm": NaN, "learning_rate": 4.6220935509274235e-05, "loss": 0.0, "step": 29 }, { "epoch": 0.909952606635071, "grad_norm": NaN, "learning_rate": 4.3353142970386564e-05, "loss": 0.0, "step": 30 }, { "epoch": 0.9402843601895735, "grad_norm": NaN, "learning_rate": 4.053522406135775e-05, "loss": 0.0, "step": 31 }, { "epoch": 0.9706161137440759, "grad_norm": NaN, "learning_rate": 3.777924554357096e-05, "loss": 0.0, "step": 32 }, { "epoch": 1.0037914691943128, "grad_norm": NaN, "learning_rate": 3.509700894014496e-05, "loss": 0.0, "step": 33 }, { "epoch": 1.034123222748815, "grad_norm": NaN, "learning_rate": 3.250000000000001e-05, "loss": 0.0, "step": 34 }, { "epoch": 1.0644549763033175, "grad_norm": NaN, "learning_rate": 2.9999339514117912e-05, "loss": 0.0, "step": 35 }, { "epoch": 1.09478672985782, "grad_norm": NaN, "learning_rate": 2.760573569460757e-05, "loss": 0.0, "step": 36 }, { "epoch": 1.1251184834123222, "grad_norm": NaN, "learning_rate": 2.53294383204969e-05, "loss": 0.0, "step": 37 }, { "epoch": 1.1554502369668247, "grad_norm": NaN, "learning_rate": 2.3180194846605367e-05, "loss": 0.0, "step": 38 }, { "epoch": 1.185781990521327, "grad_norm": NaN, "learning_rate": 2.1167208663446025e-05, "loss": 0.0, "step": 39 }, { "epoch": 1.2161137440758294, "grad_norm": NaN, "learning_rate": 1.9299099686894423e-05, "loss": 0.0, "step": 40 }, { "epoch": 1.2464454976303316, "grad_norm": NaN, "learning_rate": 1.758386744638546e-05, "loss": 0.0, "step": 41 }, { "epoch": 1.276777251184834, "grad_norm": NaN, "learning_rate": 1.602885682970026e-05, "loss": 0.0, "step": 42 }, { "epoch": 1.3071090047393366, "grad_norm": NaN, "learning_rate": 1.464072663102903e-05, "loss": 0.0, "step": 43 }, { "epoch": 1.3374407582938388, "grad_norm": NaN, "learning_rate": 1.3425421036992098e-05, "loss": 0.0, "step": 44 }, { "epoch": 1.3677725118483413, "grad_norm": NaN, "learning_rate": 1.2388144172720251e-05, "loss": 0.0, "step": 45 }, { "epoch": 1.3981042654028437, "grad_norm": NaN, "learning_rate": 1.1533337816991932e-05, "loss": 0.0, "step": 46 }, { "epoch": 1.428436018957346, "grad_norm": NaN, "learning_rate": 1.0864662381854632e-05, "loss": 0.0, "step": 47 }, { "epoch": 1.4587677725118484, "grad_norm": NaN, "learning_rate": 1.0384981238178534e-05, "loss": 0.0, "step": 48 }, { "epoch": 1.4890995260663507, "grad_norm": NaN, "learning_rate": 1.0096348454262845e-05, "loss": 0.0, "step": 49 }, { "epoch": 1.5194312796208531, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 50 }, { "epoch": 1.5194312796208531, "eval_loss": NaN, "eval_runtime": 4.1434, "eval_samples_per_second": 12.068, "eval_steps_per_second": 3.138, "step": 50 } ], "logging_steps": 1, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 25, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 1, "early_stopping_threshold": 0.0 }, "attributes": { "early_stopping_patience_counter": 1 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 5.259107997057024e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }